Upstream Data Research Articles

BrainQCNet: A Deep Learning attention-based model for the automated detection of artifacts in brain structural MRI scans

Abstract Analyses of structural MRI (sMRI) data depend on robust upstream data quality control (QC). It is also crucial that researchers seek to retain maximal amounts of data to ensure reproducible, generalizable models and to avoid wasted effort, including that of participants. The time-consuming and difficult task of manual QC evaluation has prompted the development of tools for the automatic assessment of brain sMRI scans. Existing tools have proved particularly valuable in this age of Big Data; as datasets continue to grow, reducing execution time for QC evaluation will be of considerable benefit. The development of Deep Learning (DL) models for artifact detection in structural MRI scans offers a promising avenue toward fast, accurate QC evaluation. In this study, we trained an interpretable Deep Learning model, ProtoPNet, to classify minimally preprocessed 2D slices of scans that had been manually annotated with a refined quality assessment (ABIDE 1; n = 980 scans). To evaluate the best model, we applied it to 2141 ABCD T1-weighted MRI scans for which gold-standard manual QC annotations were available. We obtained excellent accuracy: 82.4% for good quality scans (Pass), 91.4% for medium to low quality scans (Fail). Further validation using 799 T1w MRI scans from ABIDE 2 and 750 T1w MRI scans from ADHD-200 confirmed the reliability of our model. Accuracy was comparable to or exceeded that of existing ML models, with fast processing and prediction time (1 minute per scan, GPU machine, CUDA-compatible). Our attention model also performs better than traditional DL (i.e., convolutional neural network models) in detecting poor quality scans. To facilitate faster and more accurate QC prediction for the neuroimaging community, we have shared the model that returned the most reliable global quality scores as a BIDS-app (https://github.com/garciaml/BrainQCNet).

Multi-level drivers of congenital syphilis, Oregon, 2013-2021.

Despite the availability of curative penicillin treatment for syphilis during pregnancy, congenital syphilis (CS) cases have surged in the United States, including in Oregon. We conducted a retrospective analysis of individual- and county-level predictors of CS among pregnant people with syphilis in Oregon from 2013-2021. Data were collated from surveillance reports, County Health Rankings, and other sources with upstream county-level data. We used multi-level Poisson regression models to assess associations between CS and individual- and county-level factors. Among 343 people with syphilis during pregnancy, 95 (27.6%) were associated with a case of CS. At the individual-level, a history of injection drug use and a history of corrections involvement were associated with an increased risk of CS, while a recent gonorrhea diagnosis was associated with a decreased risk of CS. County-level violent crime rate, unemployment, income inequality, and adverse childhood experiences increased the risk of CS. Higher county-level socioenvironmental challenges exacerbated CS risk, particularly among people with corrections involvement. Injection drug use, corrections involvement, and county-level socioenvironmental challenges increased CS risk among pregnant people with syphilis in Oregon. Urgent interventions are needed, including innovative care models, policy reforms targeting systemic issues, and enhanced collaboration with community services to address the escalating CS crisis.

A tabular data generation framework guided by downstream tasks optimization

Recently, generative models have been gradually emerging into the extended dataset field, showcasing their advantages. However, when it comes to generating tabular data, these models often fail to satisfy the constraints of numerical columns, which cannot generate high-quality datasets that accurately represent real-world data and are suitable for the intended downstream applications. Responding to the challenge, we propose a tabular data generation framework guided by downstream task optimization (TDGGD). It incorporates three indicators into each time step of diffusion generation, using gradient optimization to align the generated fake data. Unlike the traditional strategy of separating the downstream task model from the upstream data synthesis model, TDGGD ensures that the generated data has highly focused columns feasibility in upstream real tabular data. For downstream task, TDGGD strikes the utility of tabular data over solely pursuing statistical fidelity. Through extensive experiments conducted on real-world tables with explicit column constraints and tables without explicit column constraints, we have demonstrated that TDGGD ensures increasing data volume while enhancing prediction accuracy. To the best of our knowledge, this is the first instance of deploying downstream information into a diffusion model framework.

A Grand Challenge: Digital Transformation for the Upstream Oil and Gas Industry

_ This is the fourth in a series of six articles on SPE’s Grand Challenges in Energy, formulated as the output of a 2023 workshop held by the SPE Research and Development Technical Section in Austin, Texas. Described in a JPT article last year, each of the challenges will be discussed separately in this series: geothermal energy; net-zero operations; improving recovery from tight/shale resources; digital transformation; carbon capture, utilization, and storage; and education and advocacy. _ The interval from the oil price decline of 2014–2015 through the global COVID-19 pandemic of 2020–2022 was a difficult period for the upstream oil and gas business. The industry has responded, as so many times before, by seeking to reduce structural costs with the minimum impact to required new investments, including those in nondiscretionary domains (security, including cybersecurity, and safety, health, and environmental performance) as well as those required to appropriately hedge against the emergence of new, more sustainable energy sources. Digital transformation is one of the key opportunities for the industry to systematically reduce costs across multiple business domains. While there has been active discussion of the “digital oil field” for several decades, the economic shock of the past decade revived interest in the application of digital technologies across the enterprise to improve the cost structure of businesses. Of course, at the same time, entirely new industries, such as social media, have emerged exploiting new digital technologies, including machine learning, web software and connectivity, and cloud storage and computing. These technologies have also transformed traditional industries such as retail and manufacturing. But taking the same path in the upstream industry has some special challenges and opportunities. This review focuses on digital transformation opportunities that are, to a greater or lesser degree, unique to the special data and operating environment of the modern petroleum industry. There are many valuable opportunities, including business process automations, that can and should be adopted by upstream companies, but are not different in kind from such innovations in other industries. Data Is Not the New Oil One challenge is the sheer mass and heterogeneity of upstream data. The upstream oil and gas industry is an old industry, with both business and technical records stretching back for many companies to the 19th century. These can be in paper form or a variety of digital forms reflecting the different methods of storing data since computers became a standard business and scientific tool in the 1950s. Conversion of this data to more modern formats suitable for cloud storage, for example, is not cost-free. Thus, a key principle in digital transformation is that it must be value-driven. A frequently used phrase, “data is the new oil,” is, at least for the oil and gas business itself, deeply misleading. Most of the data held by any enterprise, be it in libraries, shared data servers, or personal hard drives, is not economically useful. Much other data, while potentially valuable, requires such substantial spending on quality assurance, data curation, data transfer to points of computation, and use of (highly paid) domain experts to interpret data analysis and make business decisions that there is no pathway to reliable value based on the data.

Predicting tablet properties using In-Line measurements and evolutionary equation Discovery: A high shear wet granulation study

High shear wet granulation (HSWG) is widely used in tablet manufacturing mainly because of its advantages in improving flowability, powder handling, process run time, size distribution, and preventing segregation. In line process analytical technology measurements are essential in capturing detailed particle dynamics and presenting real-time data to uncover the complexity of the HSWG process and ultimately for process control.This study presents an opportunity to predict the properties of the granules and tablets through torque measurement of the granulation bowl and the force exerted on a novel force probe within the powder bed. Inline force measurements are found to be more sensitive than torque measurements to the granulation process. The characteristic force profiles present the overall fingerprint of the high shear wet granulation, in which the evolution of the granule formation can improve our understanding of the granulation process. This provides rich information relating to the properties of the granules, identification of the even distribution of the binder liquid, and potential granulation end point. Data were obtained from an experimental high shear mixer across a range of key process parameters using a face-centred surface response design of experiment (DoE). A closed-form analytical model was developed from the DOE matrix using the discovery of evolutionary equations. The model is able to provide a strong predictive indication of the expected tablet tensile strength based only on the data in-line. The use of a closed form mathematical equation carries notable advantages over other AI methodologies such as artificial neural networks, notably improved interpretability/interrogability, and minimal inference costs, thus allowing the model to be used for real-time decision making and process control. The capability of accurately predicting, in real time, the required compaction force required to achieve the desired tablet tensile strength from upstream data carries the potential to ensure compression machine settings rapidly reach and are maintained at optimal values, thus maximising efficiency and minimising waste.

The Impact of Upstream Oil and Gas Investment on Petroleum Production in Indonesia

This study aims to analyze the problem of whether upstream oil and gas investment will affect petroleum production or vice versa. The data used is Time series data using upstream oil and gas investment data in 2010-2020 and petroleum production data in 2010-2020 sourced from the Ministry of Energy and Mineral Resources (ESDM). The research method used in this study is a quantitative research method with a granger causality test analysis tool. The results showed that there is a one-way relationship between upstream oil and gas investment and petroleum production in Indonesia which concluded that it is necessary to increase upstream oil and gas investment to increase petroleum production in Indonesia.

Utilizing Qual2Kw software to calculate the pollution load capacity of Ciliwung River Segment IV (Depok City)

Situated in the administrative boundaries of West Java Province and DKI Jakarta Province, the Ciliwung River is a national river. Its river length is about 120 km, and its watershed area is about 425 km³ (DAS). The population of Depok City is growing at a pace of 1.79% annually, which leads to a rise in the demand for food, clothing, and housing, among other necessities. As a result of the growth of various industrial and community residential buildings to accommodate human needs, wastewater discharge into rivers will increase and the amount of pollution entering the Ciliwung River may surpass its carrying capacity if efforts are not made to control water pollution. As a result, research must be done to ascertain Segment IV Depok City's Ciliwung River Pollutant Load Capacity utilizing a simulation model and Qual2Kw software. Primary data samples of the Ciliwung River's water and pollution sources that enter it were collected for this study, in addition to firsthand field observations. Data calibration is carried out after entering hydraulic and quality data into worksheets. In order to ensure that river flow data still satisfies class II river water quality standards, modeling is done utilizing the following sources: (1) existing data; (2) upstream data of class II river water quality standards; and (3) current conditions of river flow and trial & error pollutant source data. The findings indicated that the Ciliwung River section IV, Depok City, has a somewhat contaminated water quality. Pollutant loads for TSS and COD criteria can still be accommodated in Ciliwung River section IV, Depok City. In the meantime, the BOD criteria for carrying pollutant loads has been surpassed; therefore, to meet class II water quality regulations, the BOD pollutant load needs to be reduced by 22.58% to 37.50%.

Use of Artificial Intelligence Modelling for the Dynamic Simulation of Urban Catchment Runoff

The complex topography and inherent nonlinearity affiliated with influential hydrological processes of urban catchments, coupled with limited availability of measured data, limits the prediction accuracy of conventional models. Artificial Neural Network models (ANNs) have displayed commendable progress in recognising and simulating highly complex, non-linear associations allied with input-output variables, with limited comprehension of the underlying physical processes. Therefore, this paper investigates the effectiveness and accuracy of ANN models, in estimating the urban catchment runoff, employing minimal and commonly available hydrological data variables – rainfall and upstream catchment flow data, employing two powerful supervised-learning-algorithms, Bayesian-Regularization (BR) and Levenberg-Marquardt (LM). Gardiners Creek catchment, encompassed in Melbourne, Australia, with more than thirty years of quality-checked rainfall and streamflow data was chosen as the study location. Two significant storm events that transpired within the last fifteen years - the 4th of February 2011 and the 6th of November 2018, were nominated for calibration and validation of the ANN model. The study results advocate that the use of the LM-ANN model stipulates accurate estimates of the historical storm events, with a stronger correlation and lower generalisation error, in contrast to the BR-ANN model, while the integration of upstream catchment flow alongside rainfall, vindicate for their collective impact upon the dynamics of the flow being spawned at the downstream catchment locations, significantly enhancing the model performance and providing a more cost-effective and near-realistic modelling approach that can be considered for application in studies of urban catchment responses, with limited data availability.

Who should own the data? The impact of data value creation on data ownership

With the popularization and application of the Industrial Internet of Things, equipment manufacturers as upstream enterprises can collect in real time the operational data of their downstream enterprise customers’ devices. As the notion of “data as an asset” gains acceptance, enterprises increasingly value the data value chain. In the current market mechanism, ownership of data is not clear, which hinders the creation of data value. This study establishes a theoretical analytical model that considers the influences of the benefits and losses derived from value co-creation on claiming data ownership. Benefits obtained by upstream and downstream enterprises through data and losses incurred owing to data breaches are distinct, which impact their investments in data security and data authorization. Results reveal that investments in data security by upstream businesses are affected by benefits and losses and also correlated with data ownership. Conversely, if the downstream enterprise owns the data, its expected benefits can inversely affect the upstream's data security investment—increasing the downstream's benefits can lead to reduced security investment by the upstream, even though other factors may encourage the upstream to invest more in data security. The impact of who owns the data on the security investments of both upstream and downstream enterprises becomes less pronounced when the expected benefits or potential losses for one side grow. Lastly, the current study provides guiding principles for upstream businesses to claim data ownership, thereby facilitating the exploration and utilization of data value co-creation opportunities for upstream and downstream businesses.

Adaptability and efficiency of the CMS Level-1 Global Trigger firmware implementation for Phase-2

We present details on the new Level-1 Global Trigger at CMS for the upcoming high-luminosity operation of the LHC. Our focus is on the newly developed firmware, which employs a bottom-up generic approach to enhance menu adaptability and accommodate the increase in upstream data. We also highlight our efficient pipelining strategy that ensures excellent routability at 480 MHz. Furthermore, we discuss the firmware implementation for three prototypes targeting Serenity boards, together with their current and future testing and validation endeavours.

A Review Geospatial Artificial Intelligence (GEO-AI): Implementation Of Machine Learning On Urban Planning

Geospatial Artificial Intelligence (Geo-AI) is an interesting topic in its development and application in our lives. One of them is spatial planning, which contributes to the economic and social development of a region or country. Spatial data is the main thing in this research, which maximizes the effectiveness of land use spatial data on the area as upstream data and develops GIS-based urban planning applications to display the results of analysis and predictions of urban objects automatically. On the other hand, to maximize tourism revenue, the government plans urban areas for both spatial and land use and makes a lot of spatial data based on geographical and environmental conditions. This study will analyze the benefits of Geo-AI in urban planning and the tourism sector. The method used in this study is the Systematic Literature Review (SLR), where the search for the required articles comes from electronic databases obtained using the NVivo software with article sources from Publish or Perish. This study discusses the main steps for the analysis of geospatial data that have been successful in the main areas, namely the development of applications and models, including visualization. By treating issues in geospatial artificial intelligence, the overall aim of the research is to improve the quality of life for Indonesia's growing urban population. The results of the study with the systematic literature review of Geo-AI found a gap in the research implementation of the machine learning model used where five models were compared and relevant to the geospatial dataset displayed in the form of a literature review matrix and visually included in the relevant keywords in the bibliometric analysis. Interdisciplinary results are developing and are urgently needed by both government and private stakeholders in the development of smart cities to prepare spatial planning in urban areas and strategies in optimizing technology in the field of spatial planning in implementing systems based on Geo-AI.

Photonic MMW Generation Using PM-DPMZM for Full Duplex 32×10 Gbps RoF-WDM System

Abstract This paper presents a study of a 32×10 Gbps Radio over Fiber and Wavelength Division Multiplexing (RoF-WDM) full-duplex system that uses Phase Modulators and a Dual-Port Mach-Zehnder Modulator (PMs-DPMZM) for bidirectional data transfer. The system employs Millimeter-Wave (MMW) signaling over optical fiber and focuses on selecting a technology that provides high transmission capacity per wavelength, improved spectral efficiency, and resistance against optical transmission impairments. The proposed method was validated using simulation results to confirm the efficiency of the proposed system in generating a 40 GHz signal and efficiently detecting and modulating the RF signals. The results demonstrate that the system exhibits strong resistance against dispersion, non-linear effects, and noise, delivering satisfactory performance for distances of up to 220 km. By analyzing the input power, the paper establishes a relationship between input power and signal quality, revealing that an optimal power of 0 dBm leads to an improved Quality Factor (QF) and reduced transmission errors. Furthermore, the evaluation of received optical power indicates the power level required to maintain an acceptable error rate, approximately -20.9690 dBm for downstream data transfer and -20.7245 dBm for upstream data transfer at the BER limit. The simulation performance also demonstrates the transmission efficiency achieved through a high Polarization Mode Dispersion (PMD) coefficient of up to 0.8. The analytical calculations conducted in this work provide valuable insights for optimizing and enhancing the performance of RoF-WDM networks.

Improving the Predictive Analytics of Machine-Learning Pipelines for Bridge Infrastructure Asset Management Applications: An Upstream Data Workflow to Address Data Quality Issues in the National Bridge Inventory Database

Improving the Predictive Analytics of Machine-Learning Pipelines for Bridge Infrastructure Asset Management Applications: An Upstream Data Workflow to Address Data Quality Issues in the National Bridge Inventory Database

Discrepant Semantic Diffusion Boosts Transfer Learning Robustness

Transfer learning could improve the robustness and generalization of the model, reducing potential privacy and security risks. It operates by fine-tuning a pre-trained model on downstream datasets. This process not only enhances the model’s capacity to acquire generalizable features but also ensures an effective alignment between upstream and downstream knowledge domains. Transfer learning can effectively speed up the model convergence when adapting to novel tasks, thereby leading to the efficient conservation of both data and computational resources. However, existing methods often neglect the discrepant downstream–upstream connections. Instead, they rigidly preserve the upstream information without an adequate regularization of the downstream semantic discrepancy. Consequently, this results in weak generalization, issues with collapsed classification, and an overall inferior performance. The main reason lies in the collapsed downstream–upstream connection due to the mismatched semantic granularity. Therefore, we propose a discrepant semantic diffusion method for transfer learning, which could adjust the mismatched semantic granularity and alleviate the collapsed classification problem to improve the transfer learning performance. Specifically, the proposed framework consists of a Prior-Guided Diffusion for pre-training and a discrepant diffusion for fine-tuning. Firstly, the Prior-Guided Diffusion aims to empower the pre-trained model with the semantic-diffusion ability. This is achieved through a semantic prior, which consequently provides a more robust pre-trained model for downstream classification. Secondly, the discrepant diffusion focuses on encouraging semantic diffusion. Its design intends to avoid the unwanted semantic centralization, which often causes the collapsed classification. Furthermore, it is constrained by the semantic discrepancy, serving to elevate the downstream discrimination capabilities. Extensive experiments on eight prevalent downstream classification datasets confirm that our method can outperform a number of state-of-the-art approaches, especially for fine-grained datasets or datasets dissimilar to upstream data (e.g., 3.75% improvement for Cars dataset and 1.79% improvement for SUN dataset under the few-shot setting with 15% data). Furthermore, the experiments of data sparsity caused by privacy protection successfully validate our proposed method’s effectiveness in the field of artificial intelligence security.

CSAT‐FRMET: An energy‐efficient hybrid FiWi network‐based 5G model

AbstractHybrid fiber wireless (FiWi) access networks seek to combine the vast amount of bandwidth that is available for optical networks and wireless network mobility; hence, it favors larger bandwidth request but cause the highly nonlinear lagrangian dual problem that decrease energy‐efficient network resilience. Hence, a novel Ceplato‐SAT3 model has been proposed in which the SAT3 algorithm locates the optical network unit (ONU) in an optimal position with high‐speed cost‐efficient placement and weight factor introduced into the position update to improve the exploitation and exploration capability of the algorithm. To prioritize the large bandwidth request during resource allocation, gradient priority justifier requests (GPJR) has been utilized and a novel messaging technique termed flow‐random‐message‐exchanger‐topology (FRMET) provides the index for these prioritized requests depending on QoS parameters such as notification control, reflective QoS attribute (RQA), flow bit rates and maximum packet loss rate thereby decreasing the overhead and eliminate nonlinear langrage dualand perform O2U scheduling to reduce network resilience however synchronization between different ONU clocks may cause upstream data fatal crash at the optical line terminal (OLT). Hence, curl‐trio‐opt control mechanism has been proposed in which the minimization problem is transformed into a joint optimization problem of energy consumption, traffic demand, network requests, and service flow requests by the Lyapunov technique thereby minimizing the upstream data fatal lash. The proposed model has been implemented in Python and the output obtained showed better performance in terms of ONU arrangement, throughput, energy consumption, computation, latency, and error.

Market power in smart farming and the distribution of gains in two‐stage crop production system

AbstractIn smart farming, agricultural technology providers (ATPs) wield market power in both the upstream (data collection/aggregation) and downstream (crop production) markets. Using a two‐stage Muth model, this study assesses benefit distribution from ATPs' data‐driven services in smart farming. Results show limited farmer returns from data sharing, questioning policymakers' data value focus. While data‐driven services offer notable benefits, ATPs capture a significant share due to market power. Addressing ATP market power promotes equitable rent distribution, but perfect competition risks ATPs' sustainability and R&D incentives, presenting a policy challenge for smart farming outcomes.

Assimilation of Additional Radiosonde Observation Helps Improve the Prediction of Typhoon-Related Rainfall in the Pearl River Delta

Abstract Typhoons frequently hit the Pearl River Delta (PRD), threatening the region’s dense population and assets. Typhoon precipitation forecasting in this region is challenging, in part because of the complex hydrometeorological effects over the coast and the scarcity of upstream marine meteorological observations. Typhoon Mun was formed in the South China Sea on 2 July 2019, and it brought heavy rainfall to the PRD when its center moved to the Beibu Gulf. During Typhoon Mun, an additional sounding was conducted offshore in the PRD every 12 h to assess the incremental impact on the skill of precipitation forecasting. A precipitation prediction based on the Weather Research and Forecasting (WRF) Model underestimated the 12-h accumulated precipitation over the PRD by 87%, with the Final Analysis (FNL) data from the National Centers for Environmental Prediction in the United States as initial fields. To address this issue, we implemented a solution by reconstructing the initial field through the assimilation of the additional radiosonde observations using the WRF three-dimensional variational (3D-Var) method. The prediction with the new initial fields reduced the rainfall underestimation by 24%. A difference analysis indicates that the planetary boundary layer scheme used in FNL underestimates the low-level temperature and humidity, especially after the rainfall peak. In contrast, assimilation gives a more realistic lower-tropospheric structure, significantly enhancing the moisture flux convergence around 925 hPa and divergence around 700 hPa around the PRD. Sensitivity experiments show that assimilating atmospheric thermal (i.e., temperature and humidity) profiles is more helpful than dynamic (wind) profiles in improving the rainfall prediction of the typhoon. Significance Statement The impact of typhoon-related precipitation in the Pearl River Delta (PRD) is significant. Improving the numerical forecast precision in this region poses challenges, partly due to the influences of land–sea thermal and topographic factors near the boundary layer, as well as the scarcity of upstream observational data. This study proposes a practical method to improve typhoon-related precipitation prediction from a case study of Typhoon Mun. By assimilating additional sounding observations, we obtain a more realistic structure of the lower atmosphere, better spatial patterns of water vapor fluxes, and, ultimately, better precipitation forecasts. The results of our study suggest that a more advanced observing system of vertical atmospheric structure, especially the thermal one, over the South China Sea is important for improving typhoon predictions.

Modeling and efficiency analysis of blockchain agriculture products E-commerce cold chain traceability system based on Petri net

The cold chain supply chain of e-commerce has the characteristics of long chain, dispersed production, heterogeneous information sources, etc., which is easy to cause the upstream and downstream information of the supply chain to be broken and opaque. Traditional traceability data is stored in each node enterprise, and there are problems such as low cooperation trust and poor authenticity in the upstream and downstream data transmission process of the supply chain, resulting in consumers' trust crisis on the authenticity of traceability information. Blockchain traceability system through the establishment of multi-party participation, joint maintenance of distributed database, and the use of cryptography and consensus mechanism to establish trust relationships, with data can not be tampered with, sharing of high credibility. On the basis of stochastic Petri net theory, this study constructed a blockchain e-commerce cold chain traceability model centering on the actual application of blockchain technology in logistics traceability to improve the reliability and validity of e-commerce cold chain traceability. Correlation matrix and invariants were used to analyze the validity of the model, and an isomorphic Markov chain was constructed to analyze the effectiveness evolution of the model. This study aims to deepen the understanding of the cold chain traceability system of blockchain e-commerce from the three aspects of the best optimization link, the best synergism scale, and the adaptive ability of the system to provide reference for the improvement of cold chain traceability ability by blockchain technology.

Flood risk mapping for the area with mixed floods and human impact: a case study of Yarkant River Basin in Xinjiang, China

Flooding has been causing severe consequences worldwide, including loss of human life and damage to property. Flood risk mapping, as a nonstructural measure, is efficient for flood protection and disaster alleviation. This study aims at completing the flood risk mapping of the region located at the middle reaches of the Yarkant River Oasis in western China, which has a dry climate and suffers from mixed flooding consisting of glacial outburst floods (GLOFs) and many other floods. In view of the complexity of flooding in the area, the study adopts two typical types of scenarios, namely overflow scenarios and dike-break scenarios, to complete the flood risk mapping. The MIKE FLOOD 1D/2D coupled model is used for two-dimensional flood flow simulation to compute the inundation depths and duration for flood risk assessment. The spatial overlay analysis was then used to combine the modeling results and land use/land cover layers with socioeconomic data to generate flood risk maps and damage losses under different scenarios. It is noted that evaporation and infiltration losses in the study area are not negligible because of the long flood process, the low precipitation, and dry surface/subsurface conditions. Due to the insufficient evaporation and infiltration data, a new method of synthesis loss rate is proposed to compute the evaporation/infiltration loss rate. Based on the water balance principle, the upstream and downstream flow data is utilized to calculate the water attenuation, which is then used to estimate the evaporation/infiltration loss rate. The proposed method can solve the problem of calculating evaporation/infiltration loss rates during the flooding process in such data-scarce areas. The flood risk mapping results indicate that the flood risk is high along the Yarkant River and that floods can cause severe inundation losses.

Phase-resolved real-time forecasting of three-dimensional ocean waves via machine learning and wave tank experiments

Accurate prediction of ocean waves plays an essential role in many ocean engineering applications, such as the control of wave energy converters and floating wind turbines. However, existing studies on phase-resolved wave prediction using machine learning mainly focus on two-dimensional wave data, while ocean waves are usually three-dimensional. In this work, we investigate, for the first time, the phase-resolved real-time prediction of three-dimensional waves using machine learning methods. Specifically, the wave prediction is modeled as a supervised learning task aiming at learning mapping relationships between the input historical wave data and the output future wave elevations. Four frequently-used machine learning methods are employed to tackle this task and a novel Dual-Branch Network (DBNet) is proposed for performance improvement. A group of wave basin experiments with nine directional wave spectra under three sea states are first conducted to collect the data of 3D waves. Then the wave data are used for verifying the effectiveness of the machine learning methods. The results demonstrate that the upstream wave data measured by the gauge array can be used for control-oriented wave forecasting with a forecasting horizon of more than 20 s, where the directional information provided by the upstream gauge array is vital for accurately predicting the downstream wave elevations. In addition, further investigations show that by using only local wave data (which can be easily obtained), the very short-term phase-resolved prediction (less than 5 s) can be achieved.